Publication:
Exploring Document Clustering Techniques for Personalized Peer Assessment in Exploratory Courses

Loading...
Thumbnail Image
Identifiers
Publication date
2010
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Impact
Google Scholar
Export
Research Projects
Organizational Units
Journal Issue
Abstract
Peer review has been proposed as a complement to project-based learning in courses covering a wide and heterogeneous syllabus. By reviewing peers' projects, students can explore other subjects thoroughly apart from their own project topic. This objective relies however in a proper distribution of the works to review, which is a complex and time-consuming task. Beyond simple topic selection, students may report different types of works, which influence their peers' assessment; for example, works focused on a project development approach versus in-depth literature researches. Introducing detailed metadata is time-consuming (thus users are typically reluctant) and, even more important, prone to error. In this paper we explore the potential of text mining and natural language processing technologies for automatic classification of texts, in order to facilitate the adaptation and diversification of the works assigned to the students for review, in the context of a course on Artificial Intelligence.
Description
Proceedings of: Computer-Supported Peer Review in Education: Synergies with Intelligent Tutoring Systems (CSPRED 2010), Pittsburgh, Pennsylvania USA, June 14th, 2010.
Keywords
Adaptive peer review, Document clustering, Text mining
Bibliographic citation
Proceedings of the Workshop on Computer-Supported Peer Review in Education CSPRED-2010, 5 pp